Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/serkan-ozal/browser-devtools-claude/execute-workflowsnpx skills add serkan-ozal/browser-devtools-claude --skill execute-workflowsgit clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claudeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00038 | $0.00473 |
| Opus 5 | $0.00019 | $0.00236 |
| Sonnet 5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
execute-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Execute Workflows Skill
Use this skill when the user asks to run JavaScript, execute code in the page or on the server, or batch several tool calls into one.
Rule: Use execute only
There are no separate run-JS tools. Always use the MCP tool execute.
Run JavaScript in the browser page
Use execute with page.evaluate():
// execute tool, code:
return await page.evaluate(() => document.title);
You have access to page (Playwright Page) and callTool(name, input, returnOutput?) inside the execute VM. Use await with callTool.
Run JavaScript on the server (Node VM, no DOM)
Use execute without page.evaluate() — e.g. Buffer, crypto, or multiple callTool calls:
return Buffer.from('hello').toString('base64');
Batch multiple tool calls
Use execute and call tools via await callTool(name, input, returnOutput?):
await callTool('interaction_fill', { selector: 'e3', value: '[email protected]' });
await callTool('interaction_click', { selector: 'e7', waitForNavigation: true });
const snapshot = await callTool('a11y_take-aria-snapshot', {}, true);
return snapshot;
Max 50 callTool calls per execution. Pass true as third argument to include that tool’s output in the response toolOutputs.
Node platform (backend debugging)
On Node platform, execute has no page; use callTool only. See commands/node/execute.md.
References
- Browser: commands/browser/execute.md —
page,callTool, VM API - Node: commands/node/execute.md —
callToolonly
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 54 lines · 38 tokens per session scan A bcc98e5b4b5e
execute-workflows is a skill published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 473 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.